vilm/Quyen-Pro-v0.1 is a 14.2 billion parameter instruction-tuned causal language model, part of the Qwen1.5 family, developed by vilm. This model is fine-tuned using a diverse dataset including OpenHermes-2.5, Capybara, and Intel's orca_dpo_pairs, alongside private data from Ontocord and BEE-spoke-data. It is designed for general-purpose conversational AI, leveraging SFT and DPO training methods to enhance its interactive capabilities. The model utilizes the ChatML prompt template for structured communication.
No reviews yet. Be the first to review!
Hugging Face